© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60478
    Prev
    Next
    INDEX
    Explanations

    financial contributions and support related to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARED
    -0.06
     Jacob
    -0.05
    oola
    -0.05
    hti
    -0.05
     Combo
    -0.05
    WebHost
    -0.05
    aniel
    -0.05
    TECTED
    -0.05
    inecraft
    -0.05
    oord
    -0.05
    POSITIVE LOGITS
    insky
    0.07
    hydrate
    0.07
    itize
    0.07
    seg
    0.07
    ÑĢÑĸб
    0.06
    jourd
    0.06
    iyan
    0.06
    lijk
    0.06
    ystick
    0.06
    ë¶Ħ
    0.06
    Activations Density 0.001%

    No Known Activations